Speech recognition in many morphologically rich languages suffers from a very high out-of-vocabulary (OOV) ratio. Earlier work has shown that vocabulary decomposition methods can ...
Most affinity-based grouping methods only model the inclusive relation among the data. When the data set contains a significant amount of noise data that should not be included in...
In this paper we derive a generic form of structural decomposition for the constraint satisfaction problem, which we call a guarded decomposition. We show that many existing decom...
We address the problem of detecting consensus motifs, that occur with subtle variations, across multiple sequences. These are usually functional domains in DNA sequences such as t...
Abstract--In this paper we address the problem of unsupervised discovery of action classes in video data. Different from all existing methods thus far proposed for this task, we pr...